ClawHub
Back to skill

Security audit

Stay AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only Stay AI connector that uses OOMOL's CLI to fetch account, subscription, and order data.

Install only if you are comfortable letting the agent query Stay AI account, subscription, and order information through your OOMOL-connected account. Review the exact action and payload for any future write or destructive action, but this version only lists read-oriented actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger language is excessively broad: 'Use this skill for ANY Stay AI request' encourages unconditional invocation whenever Stay AI is mentioned, without narrowing to supported read-only use cases or requiring task qualification. This can cause the agent to route unrelated, sensitive, or higher-risk requests through the skill automatically, increasing the chance of unintended data access or misuse, even though the listed actions are currently read-oriented.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.